[PATCH 19/21] Btrfs: fix unexpected return value of fiemap

[David Sterba <dsterba@suse.com>]

From: Liu Bo <bo.li.liu@oracle.com>

commit 2d324f59f343967a03eeb2690f0ff178304d0687 upstream.

btrfs's fiemap is supposed to return 0 on success and return < 0 on
error. however, ret becomes 1 after looking up the last file extent:

  btrfs_lookup_file_extent ->
    btrfs_search_slot(..., ins_len=0, cow=0)

and if the offset is beyond EOF, we'll get 'path' pointed to the place
of potentail insertion, and ret == 1.

This may confuse applications using ioctl(FIEL_IOC_FIEMAP).

Signed-off-by: Liu Bo <bo.li.liu@oracle.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/extent_io.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 392592dc7010..57fccc420697 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -4385,8 +4385,12 @@ int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 	if (ret < 0) {
 		btrfs_free_path(path);
 		return ret;
+	} else {
+		WARN_ON(!ret);
+		if (ret == 1)
+			ret = 0;
 	}
-	WARN_ON(!ret);
+
 	path->slots[0]--;
 	btrfs_item_key_to_cpu(path->nodes[0], &found_key, path->slots[0]);
 	found_type = found_key.type;
-- 
2.7.1